Wei Cheng

wchengad's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 4 days ago

ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts

Paper • 2507.20939 • Published 5 days ago • 56

upvoted a paper 10 days ago

Step-Audio 2 Technical Report

Paper • 2507.16632 • Published 11 days ago • 59

upvoted a paper 11 days ago

GR-3 Technical Report

Paper • 2507.15493 • Published 12 days ago • 44

upvoted 3 papers 18 days ago

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

Paper • 2507.05255 • Published 26 days ago • 68

SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation

Paper • 2507.09862 • Published 19 days ago • 48

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

Paper • 2507.08441 • Published 22 days ago • 59

upvoted 3 papers about 2 months ago

OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation

Paper • 2506.07977 • Published Jun 9 • 41

FlexPainter: Flexible and Multi-View Consistent Texture Generation

Paper • 2506.02620 • Published Jun 3 • 14

Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers

Paper • 2506.03065 • Published Jun 3 • 27

upvoted 4 papers 2 months ago

VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning

Paper • 2505.23504 • Published May 29 • 7

ViStoryBench: Comprehensive Benchmark Suite for Story Visualization

Paper • 2505.24862 • Published May 30 • 31

KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models

Paper • 2505.16707 • Published May 22 • 45

Emerging Properties in Unified Multimodal Pretraining

Paper • 2505.14683 • Published May 20 • 133

upvoted 3 papers 3 months ago

Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets

Paper • 2505.07747 • Published May 12 • 61

Step1X-Edit: A Practical Framework for General Image Editing

Paper • 2504.17761 • Published Apr 24 • 93

StyleMe3D: Stylization with Disentangled Priors by Multiple Encoders on 3D Gaussians

Paper • 2504.15281 • Published Apr 21 • 24

upvoted a paper 4 months ago

OmniSVG: A Unified Scalable Vector Graphics Generation Model

Paper • 2504.06263 • Published Apr 8 • 178

upvoted a paper 9 months ago

MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D

Paper • 2411.02336 • Published Nov 4, 2024 • 25